Model: GELU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1813 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.2591. Min Range: -5.2591

Max Act: 5.2591. Min Act: -0.1700

Data Index: 648942 (C4 (Web Text))

Max Activating Token Index: 696

Text #1

Max Range: 5.2591. Min Range: -5.2591

Max Act: 5.2591. Min Act: -0.1700

Data Index: 1009753 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 5.2591. Min Range: -5.2591

Max Act: 5.1653. Min Act: -0.1700

Data Index: 732399 (C4 (Web Text))

Max Activating Token Index: 594

Text #3

Max Range: 5.2591. Min Range: -5.2591

Max Act: 5.1966. Min Act: -0.1700

Data Index: 1283572 (C4 (Web Text))

Max Activating Token Index: 800

Text #4

Max Range: 5.2591. Min Range: -5.2591

Max Act: 5.1653. Min Act: -0.1700

Data Index: 828163 (C4 (Web Text))

Max Activating Token Index: 688

Text #5

Max Range: 5.2591. Min Range: -5.2591

Max Act: 5.1653. Min Act: -0.1700

Data Index: 524444 (C4 (Web Text))

Max Activating Token Index: 481

Text #6

Max Range: 5.2591. Min Range: -5.2591

Max Act: 5.1341. Min Act: -0.1700

Data Index: 634271 (C4 (Web Text))

Max Activating Token Index: 538

Text #7

Max Range: 5.2591. Min Range: -5.2591

Max Act: 5.1653. Min Act: -0.1700

Data Index: 1238898 (C4 (Web Text))

Max Activating Token Index: 685

Text #8

Max Range: 5.2591. Min Range: -5.2591

Max Act: 5.1653. Min Act: -0.1700

Data Index: 550284 (C4 (Web Text))

Max Activating Token Index: 689

Text #9

Max Range: 5.2591. Min Range: -5.2591

Max Act: 5.1341. Min Act: -0.1700

Data Index: 1270645 (C4 (Web Text))

Max Activating Token Index: 586

Text #10

Max Range: 5.2591. Min Range: -5.2591

Max Act: 5.1341. Min Act: -0.1700

Data Index: 204502 (C4 (Web Text))

Max Activating Token Index: 186

Text #11

Max Range: 5.2591. Min Range: -5.2591

Max Act: 5.1028. Min Act: -0.1700

Data Index: 452151 (C4 (Web Text))

Max Activating Token Index: 681

Text #12

Max Range: 5.2591. Min Range: -5.2591

Max Act: 5.1341. Min Act: -0.1700

Data Index: 9706 (C4 (Web Text))

Max Activating Token Index: 913

Text #13

Max Range: 5.2591. Min Range: -5.2591

Max Act: 5.1028. Min Act: -0.1700

Data Index: 793475 (C4 (Web Text))

Max Activating Token Index: 679

Text #14

Max Range: 5.2591. Min Range: -5.2591

Max Act: 5.1341. Min Act: -0.1700

Data Index: 981626 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 5.2591. Min Range: -5.2591

Max Act: 5.1341. Min Act: -0.1700

Data Index: 537584 (C4 (Web Text))

Max Activating Token Index: 828

Text #16

Max Range: 5.2591. Min Range: -5.2591

Max Act: 5.1341. Min Act: -0.1700

Data Index: 443653 (C4 (Web Text))

Max Activating Token Index: 710

Text #17

Max Range: 5.2591. Min Range: -5.2591

Max Act: 5.0716. Min Act: -0.1700

Data Index: 394375 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 5.2591. Min Range: -5.2591

Max Act: 5.1341. Min Act: -0.1700

Data Index: 282492 (C4 (Web Text))

Max Activating Token Index: 817

Text #19

Max Range: 5.2591. Min Range: -5.2591

Max Act: 5.1341. Min Act: -0.1700

Data Index: 641706 (C4 (Web Text))

Max Activating Token Index: 628